V-CECE：通过概念编辑生成视觉反事实解释
V-CECE: Visual Counterfactual Explanations via Conceptual Edits
AI总结：
V-CECE通过概念编辑生成反事实解释，无需训练即可产生人类水平的可解释性结果。
摘要：
最近的黑盒反事实生成框架未能考虑所提出编辑的语义内容，而主要依赖训练来指导生成过程。我们提出了一种新颖的、即插即用的黑盒反事实生成框架，该框架基于最优编辑的理论保证，逐步提出编辑以生成具有零训练的人类水平反事实解释。我们的框架利用预训练的图像编辑扩散模型，并且不访问分类器的内部，导致可解释的反事实生成过程。在整个实验过程中，我们通过使用卷积神经网络（CNN）、视觉变换器（ViT）和大视觉语言模型（LVLM）分类器，展示了人类推理与神经模型行为之间的解释差距，并通过全面的人类评估加以验证。
英文摘要：
Recent black-box counterfactual generation frameworks fail to take into account the semantic content of the proposed edits, while relying heavily on training to guide the generation process. We propose a novel, plug-and-play black-box counterfactual generation framework, which suggests step-by-step edits based on theoretical guarantees of optimal edits to produce human-level counterfactual explanations with zero training. Our framework utilizes a pre-trained image editing diffusion model, and operates without access to the internals of the classifier, leading to an explainable counterfactual generation process. Throughout our experimentation, we showcase the explanatory gap between human reasoning and neural model behavior by utilizing both Convolutional Neural Network (CNN), Vision Transformer (ViT) and Large Vision Language Model (LVLM) classifiers, substantiated through a comprehensive human evaluation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
